Instructions to use schneewolflabs/A1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use schneewolflabs/A1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="schneewolflabs/A1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("schneewolflabs/A1")
model = AutoModelForCausalLM.from_pretrained("schneewolflabs/A1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use schneewolflabs/A1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schneewolflabs/A1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schneewolflabs/A1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/schneewolflabs/A1

SGLang

How to use schneewolflabs/A1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "schneewolflabs/A1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schneewolflabs/A1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "schneewolflabs/A1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schneewolflabs/A1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use schneewolflabs/A1 with Docker Model Runner:
```
docker model run hf.co/schneewolflabs/A1
```

A1 / README.md

nbeerbower

Add A1: reasoning SFT of A0i-12B on BigDenker-SFT (merged)

b8d069e verified 12 days ago

preview code

raw

history blame contribute delete

4.83 kB

	---
	base_model: schneewolflabs/A0i-12B
	datasets:
	- schneewolflabs/BigDenker-SFT
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- reasoning
	- thinking
	- chain-of-thought
	- mistral
	- sft
	- lora
	license: apache-2.0
	---

	# A1

	A1 is a reasoning-tuned version of [`schneewolflabs/A0i-12B`](https://huggingface.co/schneewolflabs/A0i-12B) (Mistral Nemo–class, 12B). It was supervised-fine-tuned on [`schneewolflabs/BigDenker-SFT`](https://huggingface.co/datasets/schneewolflabs/BigDenker-SFT) to produce explicit `<think>…</think>` chain-of-thought before its final answer.

	## What's different from the base model

	The base A0i-12B does not reason — given a prompt it answers directly. A1 produces a reasoning trace inside `<think></think>` and then the answer, in the Qwen3 thinking convention.

	The reasoning tokens were added without resizing the vocabulary. A0i's tokenizer ships with 986 unused reserved slots (`<SPECIAL_14>`…`<SPECIAL_999>`); ten of these were repurposed in place (token IDs unchanged, so embeddings were not resized):

	\| ID \| token \| ID \| token \|
	\|----\|-------\|----\|-------\|
	\| 14 \| `<think>` \| 19 \| `</tool_response>` \|
	\| 15 \| `</think>` \| 20 \| `<\\|vision_start\\|>` \|
	\| 16 \| `<tool_call>` \| 21 \| `<\\|vision_end\\|>` \|
	\| 17 \| `</tool_call>` \| 22 \| `<\\|image_pad\\|>` \|
	\| 18 \| `<tool_response>` \| 23 \| `<\\|video_pad\\|>` \|

	Before training, these rows (which were zero/untrained in the base) were initialized from the mean of their surface string's sub-token embeddings (computed separately for `embed_tokens` and `lm_head`, which are untied), with a small symmetry-breaking perturbation. They were then trained as part of the finetune.

	> Note: the vision/tool tokens exist for chat-template completeness. A1 is a text-only model and was not trained on vision or tool-calling data.

	## Usage

	A1 uses a Qwen3-style chat template (bundled as `chat_template.jinja`). The template injects `<think>\n` as the assistant prefix, so the model continues with its reasoning, emits `</think>`, then the answer. Always use the chat template — using the model without it will not trigger reasoning.

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	tok = AutoTokenizer.from_pretrained("schneewolflabs/A1")
	model = AutoModelForCausalLM.from_pretrained(
	"schneewolflabs/A1", dtype=torch.bfloat16, device_map="auto"
	)

	messages = [
	{"role": "system", "content": "You are a helpful assistant."},
	{"role": "user", "content": "A bat and ball cost $1.10. The bat is $1.00 more than the ball. How much is the ball?"},
	]
	enc = tok.apply_chat_template(
	messages, add_generation_prompt=True, return_tensors="pt", return_dict=True
	).to(model.device)
	out = model.generate(**enc, max_new_tokens=1024, do_sample=False)
	print(tok.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=False))
	```

	The output has the form `…reasoning…</think>\n\n…final answer…<\|im_end\|>`.

	## Training

	- Method: SFT, 1 epoch, via the Merlina training system (grimoire `SFTLoss`, prompt-masked completion).
	- Adaptation: LoRA (r=64, α=128, dropout 0.05) on attention + MLP projections, plus `embed_tokens` and `lm_head` as fully-trained `modules_to_save` (required so the repurposed token rows actually learn).
	- Hyperparameters: lr 2e-5 (cosine, 5% warmup), effective batch 16 (bs 1 × grad-accum 16), max sequence length 4096, bf16, seed 42.
	- Split: 90% train / 10% held-out eval (random, seed 42).
	- Result: train loss 1.22 → 0.687; held-out eval loss ≈ 0.653 (eval ≤ train — no overfitting at 1 epoch).
	- The conservative learning rate plus the semantic embedding initialization were chosen to add reasoning while limiting drift of the base model's general token representations (the full embedding/lm_head matrices were trainable).

	## Evaluation notes

	Behavioral checks show coherent step-by-step reasoning that generalizes beyond the training distribution — e.g. it solves the bat-and-ball problem correctly ($0.05) and explicitly rejects the common intuitive-trap answer.

	## Limitations

	- Always-on thinking: the template starts every assistant turn with `<think>`; the model reasons even on trivial prompts. A non-thinking path exists via the template (`enable_thinking=False` injects an empty `<think></think>`) but was not specifically tuned.
	- Single-source SFT: trained on one dataset/style (BigDenker), so reasoning phrasing is fairly homogeneous.
	- One epoch / conservative LR: a deliberate, safe first pass — not exhaustively tuned.
	- Inherits all limitations and biases of the base model and the SFT data.

	## Provenance

	Base: `schneewolflabs/A0i-12B` · Data: `schneewolflabs/BigDenker-SFT` · Tokenizer/template: repurposed reserved tokens + Qwen3 chat template.